Information processing device

Abstract

To estimate traffic volume at a point where a traffic volume survey is not performed based on position information of vehicles transmitted from a part of the vehicles and traffic volume at a point where the traffic volume survey is performed.SOLUTION: An information processing device includes: an acquisition section which acquires whole traffic volume at an observation point where the whole traffic volume being the traffic volume of whole vehicles including first vehicles capable of transmitting position information of self vehicles and a second vehicle not capable of transmitting position information is observed and also acquires the position information of the first vehicles on a whole road including the observation point and a non-observation point where the whole traffic volume is not observed; and an estimation section which estimates the whole traffic volume at the non-observation point based on a traffic volume ratio being the ratio between the whole traffic volume at the observation point through which the first vehicles traveling on the non-observation point recently pass, which is calculated from the whole traffic volume at the observation point and the position information of the first vehicles on a whole road acquired by the acquisition section, and the traffic volume of the first vehicles, and also based on the traffic volume of the first vehicles at the non-observation point.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] This disclosure relates to an information processing apparatus.

Background Art

[0002] Patent Document 1 discloses a technique capable of analyzing traffic flow by a relatively simple method.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The technique of Patent Document 1 determines the traffic flow of vehicles traveling in a predetermined area of a road using the position information transmitted from the vehicles. However, since there are vehicles that cannot transmit position information, the determination accuracy of traffic flow in the technique of Patent Document 1 is not sufficient. In addition, there is also a method in which an investigator manually measures the traffic volume without using information from vehicles. However, since it is difficult to manually measure the traffic volume of all roads, the traffic volume at locations where traffic volume surveys have not been conducted could not be grasped.

[0005] Therefore, an object of this disclosure is to provide an information processing apparatus capable of estimating the traffic volume at locations where traffic volume surveys have not been conducted based on the position information of the vehicle transmitted from some vehicles and the traffic volume at locations where traffic volume surveys have been conducted.

Means for Solving the Problems

[0006] The information processing apparatus according to claim 1 is at an observation point where the overall traffic volume, which is the traffic volume of the entire vehicle including a first vehicle capable of transmitting the position information of its own vehicle and a second vehicle incapable of transmitting the position information, is observed. Output from a pre-trained model that has been machine-learned to output values ​​for the volume of vehicles traveling at the aforementioned observation point from an image.An acquisition unit that acquires the total traffic volume and the position information of the first vehicle on the entire road, including the observation point and non-observation points where the total traffic volume is not observed. Based on the trajectory formed by the position information of the first vehicle acquired by the acquisition unit, the branching ratio of straight, right turn, left turn, and U-turn at each intersection of the first vehicle is determined, and based on the trajectory and the time information included in the position information, the travel speed of the first vehicle at the observation point and the non-observation point is determined by the identification unit. The system includes an estimation unit that estimates the total traffic volume at a non-observation point based on a traffic volume ratio calculated from the total traffic volume at the observation point acquired by the acquisition unit and the position information of the first vehicle on the entire road, which is the ratio of the total traffic volume at the observation point most recently passed by the first vehicle traveling at the non-observation point to the traffic volume of the first vehicle, and the traffic volume of the first vehicle at the non-observation point.

[0007] In the information processing device according to claim 1, the acquisition unit acquires the total traffic volume at the observation point and the position information of the first vehicle on the entire road. For example, the acquisition unit acquires the total traffic volume at the observation point output from a trained model that has been trained to output a value that measures the traffic volume of vehicles traveling at the observation point from an image of the observation point. The estimation unit then estimates the total traffic volume at the non-observation point based on the traffic volume ratio of the observation point that the first vehicle traveling at the non-observation point has most recently passed, and the traffic volume of the first vehicle at the non-observation point. As a result, the information processing device can estimate the total traffic volume at the non-observation point, which is a point where a traffic volume survey is not conducted, based on the position information of the first vehicle transmitted from the first vehicle and the total traffic volume at the observation point, which is a point where a traffic volume survey is conducted.

[0008] The information processing device according to claim 2, in claim 1, the estimation unit, when there are multiple first vehicles traveling through the non-observation point, calculates the traffic volume ratio of the observation point that each of the multiple first vehicles has most recently passed. The average value Based on the traffic volume of the first vehicle at the non-observation point, the total traffic volume at the non-observation point is estimated.

[0009] In the information processing device according to claim 2, if there are multiple first vehicles traveling at a non-observation point, the estimation unit estimates the total traffic volume at the non-observation point based on the traffic volume ratio of the observation points that each of the multiple first vehicles has most recently passed, and the traffic volume of the first vehicles at the non-observation point. As a result, the information processing device can estimate the total traffic volume at the non-observation point based on the total traffic volume of the observation points that each of the multiple first vehicles has most recently passed.

[0010] The information processing device according to claim 3, in claim 1 or 2, the estimation unit estimates the total traffic volume at a predetermined observation point based on the traffic volume ratio at a predetermined observation point and the traffic volume of the first vehicle at the predetermined observation point, which are calculated from the total traffic volume at the observation point and the position information of the first vehicle on the entire road, acquired by the acquisition unit.

[0011] In the information processing device according to claim 3, the estimation unit estimates the total traffic volume at a predetermined observation point based on the traffic volume ratio of the predetermined observation point and the traffic volume of the first vehicle at the predetermined observation point. As a result, the information processing device can also estimate the total traffic volume at an observation point where a traffic volume survey is being conducted.

[0012] The information processing device according to claim 4, in claim 3, wherein the period for which the estimation unit estimates the total traffic volume at a predetermined observation point is shorter than the period for which the acquisition unit acquires the total traffic volume at the observation point.

[0013] In the information processing device according to claim 4, the period during which the estimation unit estimates the total traffic volume at a predetermined observation point is shorter than the period during which the acquisition unit acquires the total traffic volume at the observation point. As a result, the information processing device can grasp the total traffic volume by estimating the total traffic volume at the observation point without waiting to acquire the total traffic volume.

[0014] The information processing apparatus according to claim 5, in any one of claims 1 to 4, when a plurality of traffic volume ratios of the observation point are provided according to time zones, the estimation unit estimates the total traffic volume of the non-observation point or the predetermined observation point based on the traffic volume ratio closest to the current date and time.

[0015] In the information processing apparatus according to claim 5, when a plurality of traffic volume ratios of the observation point are provided according to time zones, the estimation unit estimates the total traffic volume of the non-observation point or the predetermined observation point based on the traffic volume ratio closest to the current date and time. Thereby, in the information processing apparatus, the total traffic volume can be estimated based on a highly reliable traffic volume ratio corresponding to the time zone closest to the current date and time.

Advantages of the Invention

[0016] As described above, in the information processing apparatus according to the present disclosure, based on the position information of the vehicle transmitted from some vehicles and the traffic volume at the point where the traffic volume survey is being conducted, the traffic volume at the point where the traffic volume survey is not being conducted can be estimated.

Brief Description of the Drawings

[0017] [Figure 1] It is a diagram showing a schematic configuration of an estimation system. [Figure 2] It is a block diagram showing the hardware configuration of a server. [Figure 3] It is a block diagram showing an example of the functional configuration of a server. [Figure 4] It is a flowchart showing the flow of calculation processing. [Figure 5] It is a flowchart showing the flow of estimation processing. [Figure 6] It is an explanatory diagram explaining a non-observation point where the total traffic volume is estimated.

Embodiments for Carrying Out the Invention

[0018] Hereinafter, the estimation system 10 according to the present embodiment will be described. FIG. 1 is a diagram showing a schematic configuration of the estimation system 10.

[0019] As shown in FIG. 1, the estimation system 10 includes a server 20, a vehicle 40, and an observation device 60. The connected vehicle 42 included in the server 20 and the vehicle 40 is connected via a network N1. The server 20 and the observation device 60 are connected via a network N2.

[0020] The server 20 is a server computer owned by a predetermined operator. The server 20 is an example of an "information processing device".

[0021] The vehicle 40 includes the above-mentioned connected vehicle 42 and a non-connected vehicle 44. The connected vehicle 42 is a so-called connected car that can transmit the vehicle information of its own vehicle to the server 20. The vehicle information includes, for example, identification information for identifying the connected vehicle 42 (hereinafter, may also be referred to as "vehicle ID (Identification)"), position information, time information, and the like. The position information is information indicating the position of the connected vehicle 42. The time information is information indicating the date and time when the connected vehicle 42 acquired the position information. The connected vehicle 42 acquires position information at regular intervals, for example, by using a position information acquisition system such as GNSS (Global Navigation Satelite System). In addition, the connected vehicle 42 acquires the date and time measured by an in-vehicle clock unit (not shown) when the position information is acquired as time information. When the connected vehicle 42 acquires the position information and the time information, it stores them in a predetermined storage area and transmits them to the server 20 together with the identification information at a predetermined timing.

[0022] The non-connected vehicle 44 is a vehicle 40 that cannot transmit the vehicle information of its own vehicle to the server 20. The connected vehicle 42 is an example of a "first vehicle", and the non-connected vehicle 44 is an example of a "second vehicle".

[0023] The observation device 60 is a computer device installed at an observation point on a road that transmits observation information obtained from vehicles 40 traveling at the observation point to the server 20. The observation information includes, for example, identification information (hereinafter sometimes referred to as "device ID") that identifies the observation device 60, location information, image information, and time information. The location information indicates the location of the observation device 60. The image information indicates an image taken of a predetermined range of the observation point by a camera equipped with the observation device 60. The time information indicates the date and time when the observation device 60 took the image. When the observation device 60 acquires the image information and time information, it stores them in a predetermined memory area and transmits them to the server 20 along with the identification information and location information at a predetermined timing.

[0024] Next, we will describe the hardware configuration of server 20. Figure 2 is a block diagram showing the hardware configuration of server 20.

[0025] As shown in Figure 2, the server 20 comprises a CPU (Central Processing Unit) 21, ROM (Read Only Memory) 22, RAM (Random Access Memory) 23, storage unit 24, input unit 25, display unit 26, and communication unit 27. Each component is connected to the others via a bus 28 so that they can communicate with each other.

[0026] The CPU 21 is a central processing unit that executes various programs and controls various components. Specifically, the CPU 21 reads programs from the ROM 22 or memory unit 24 and executes them using the RAM 23 as a working area. The CPU 21 controls each of the above components and performs various calculations according to the programs recorded in the ROM 22 or memory unit 24.

[0027] ROM22 stores various programs and data. RAM23 temporarily stores programs or data as a working area.

[0028] The memory unit 24 is composed of a storage device such as an HDD (Hard Disk Drive), SSD (Solid State Drive), or flash memory, and stores various programs and data. The memory unit 24 stores an information processing program 24A that causes the CPU 21 to execute calculation and estimation processes described later. The memory unit 24 also stores a trained model that has been trained to output values ​​of the traffic volume of vehicles 40 traveling at an observation point from images of the observation point.

[0029] The input unit 25 includes a pointing device such as a mouse, a keyboard, a microphone, and a camera, and is used for various types of input. The display unit 26 is, for example, a liquid crystal display and displays various types of information.

[0030] The communication unit 27 is an interface for communicating with other devices. For such communication, a wired communication standard such as Ethernet® or FDDI, or a wireless communication standard such as 4G, 5G, Bluetooth®, or Wi-Fi® may be used.

[0031] Next, we will describe the functional configuration of server 20. Figure 3 is a block diagram showing an example of the functional configuration of server 20.

[0032] As shown in Figure 3, the CPU 21 of the server 20 has an acquisition unit 21A, a calculation unit 21B, and an estimation unit 21C as its functional configuration. Each functional configuration is realized by the CPU 21 reading and executing an information processing program 24A stored in the storage unit 24.

[0033] The acquisition unit 21A acquires the total traffic volume at the observation point and the location information of connected vehicles 42 along the entire road, including the observation point and non-observation points where the total traffic volume is not observed. The observation point and non-observation points are areas within the road, for example, the area from one intersection to another. Non-observation points are locations where the observation device 60 is not installed.

[0034] The acquisition unit 21A acquires observation information transmitted from observation devices 60 installed at each observation point. Next, the acquisition unit 21A classifies the image information of each observation point into time zone groups based on time information and inputs the image information of each group into a trained model stored in the storage unit 24. For example, when the acquisition unit 21A acquires the total traffic volume of observation point A during the time zone from 8:00 to 9:00, it performs the following processing. First, the acquisition unit 21A inputs the image information of the 8:00 to 9:00 time zone groups from the past month into the trained model, one day at a time. Then, the acquisition unit 21A acquires the average value of multiple values ​​output from the trained model for the past month as the total traffic volume of observation point A during the 8:00 to 9:00 time zone. The acquisition unit 21A acquires the total traffic volume of each observation point during each time zone by performing the above processing for the image information of each group at each observation point. The total traffic volume of the observation point acquired by the acquisition unit 21A is stored in the storage unit 24, linked to the device ID and time zone. Furthermore, the acquisition unit 21A periodically acquires the total traffic volume at the observation points described above and periodically updates the data stored in the storage unit 24.

[0035] The acquisition unit 21A acquires vehicle information transmitted from connected vehicles 42 traveling on the road as location information for all connected vehicles 42 on the road.

[0036] The calculation unit 21B calculates the total traffic volume of connected vehicles 42 on the road based on the observation information and vehicle information acquired by the acquisition unit 21A.

[0037] An example of how the traffic volume of connected vehicles 42 at an observation point is calculated is described below. For example, when the calculation unit 21B calculates the traffic volume of connected vehicles 42 at observation point A during the time period from 8:00 to 9:00, it performs the following processing. First, based on the observation information and vehicle information, the calculation unit 21B identifies the number of connected vehicles 42 passing through observation point A during the time period from 8:00 to 9:00 for each day over the past month. Then, the calculation unit 21B calculates the average daily number of passing vehicles over the past month as the traffic volume of connected vehicles 42 at observation point A during the time period from 8:00 to 9:00. The calculation unit 21B calculates the traffic volume of connected vehicles 42 at each observation point during each time period by performing the above processing for each time period at each observation point. The traffic volume of connected vehicles 42 at each observation point calculated by the calculation unit 21B is stored in the storage unit 24 as a list of passing vehicles per unit time, divided into each time period at each observation point.

[0038] Next, an example of how the traffic volume of connected vehicles 42 at non-observation points is calculated will be explained. For example, when the calculation unit 21B calculates the traffic volume of connected vehicles 42 at non-observation point A during the time period from 8:00 to 9:00, it performs the following processing. First, based on the observation information and vehicle information, the calculation unit 21B identifies the number of connected vehicles 42 passing through non-observation point A during the time period from 8:00 to 9:00 for each day over the past month. Then, the calculation unit 21B calculates the average daily number of vehicles passing through over the past month as the traffic volume of connected vehicles 42 at non-observation point A during the time period from 8:00 to 9:00. The calculation unit 21B calculates the traffic volume of connected vehicles 42 at each non-observation point during each time period by performing the above processing for each time period at each non-observation point. The traffic volume of connected vehicles 42 at non-observation points calculated by the calculation unit 21B is stored in the storage unit 24 as a list of vehicles passing through per unit time, divided into each time period at each non-observation point. Furthermore, the calculation unit 21B periodically calculates the traffic volume of connected vehicles 42 at the observation points and non-observation points described above, and periodically updates the data stored in the storage unit 24.

[0039] Furthermore, the calculation unit 21B calculates the traffic volume ratio, which is the ratio of the total traffic volume at an observation point to the traffic volume of connected vehicles 42, from the total traffic volume at the observation point acquired by the acquisition unit 21A and the location information of connected vehicles 42 on the entire road. Specifically, the calculation unit 21B calculates the traffic volume ratio for each observation point in each time period. For example, the calculation unit 21B acquires the total traffic volume (e.g., 6 vehicles) and the traffic volume of connected vehicles 42 (e.g., 2 vehicles) at observation point A in the time period from 8:00 to 9:00 from the storage unit 24. In this case, the calculation unit 21B calculates the traffic volume ratio for observation point A in the time period from 8:00 to 9:00 as "3:1". The traffic volume ratio calculated by the calculation unit 21B is stored in the storage unit 24, linked to the device ID and time period. In addition, the calculation unit 21B periodically calculates the traffic volume ratio for each observation point in each time period and periodically updates the traffic volume ratio stored in the storage unit 24.

[0040] The estimation unit 21C estimates the total traffic volume at both non-observed and observed locations. Details of this will be described later.

[0041] Figure 4 is a flowchart showing the calculation process flow by which the server 20 calculates the traffic volume ratio at observation points. The CPU 21 reads the information processing program 24A from the memory unit 24, loads it into the RAM 23, and executes it to perform the calculation process.

[0042] In step S10 shown in Figure 4, the CPU 21 obtains the total traffic volume for each observation point. Specifically, the CPU 21 obtains the total traffic volume for each observation point for each time period from the storage unit 24. Then, the CPU 21 proceeds to step S11.

[0043] In step S11, the CPU 21 obtains the traffic volume of connected vehicles 42 at the observation points. Specifically, the CPU 21 obtains the traffic volume of connected vehicles 42 at each observation point for each time period from the storage unit 24. Then, the CPU 21 proceeds to step S12.

[0044] In step S12, the CPU 21 calculates the traffic volume ratio for each observation point during each time period from the total traffic volume at the observation point acquired in step S10 and the traffic volume of connected vehicles 42 at the observation point acquired in step S11. Specifically, the CPU 21 calculates the traffic volume ratio between the total traffic volume and the traffic volume of connected vehicles 42 that are common to the time period and observation point. Then, the CPU 21 terminates the calculation process.

[0045] Figure 5 is a flowchart showing the flow of the estimation process in which the server 20 estimates the total traffic volume at non-observed locations. The CPU 21 reads the information processing program 24A from the memory unit 24, loads it into the RAM 23, and executes it, thereby performing the estimation process.

[0046] In step S20 shown in Figure 5, the CPU 21 acquires the traffic volume of connected vehicles 42 at non-observed locations. Specifically, based on observation information and vehicle information transmitted from connected vehicles 42 traveling on the road, the CPU 21 identifies connected vehicles 42 traveling at non-observed locations (hereinafter referred to as "non-observed locations for estimation") where the total traffic volume specified by the user is estimated. The CPU 21 then acquires the number of connected vehicles 42 traveling at the non-observed locations for estimation as the traffic volume of connected vehicles 42 at the non-observed locations for estimation. After that, the CPU 21 proceeds to step S21.

[0047] In step S21, the CPU 21 obtains the traffic volume ratio of the observation point most recently passed by the connected vehicle 42 traveling through the non-observation point to be estimated. Specifically, the CPU 21 identifies the observation point most recently passed by the connected vehicle 42 from the trajectory formed by the location information contained in the vehicle information transmitted from the connected vehicle 42 and the observation information. The CPU 21 then obtains the traffic volume ratio of the identified observation point from the storage unit 24. After that, the CPU 21 proceeds to step S22.

[0048] In step S22, the CPU 21 estimates the total traffic volume of the non-observed location based on the traffic volume of the connected vehicle 42 at the non-observed location to be estimated, which was obtained in step S20, and the traffic volume ratio of the observation location that the connected vehicle 42 most recently passed, which was obtained in step S21. Then, the CPU 21 terminates the estimation process.

[0049] Next, using Figure 6, we will explain a specific example of the total traffic volume at non-observed locations estimated by the CPU21.

[0050] Figure 6(A) is the first explanatory diagram illustrating a specific example of the total traffic volume at a non-observed location estimated by the CPU 21. As an example, Figure 6(A) shows a vehicle 40 traveling at non-observed location A, which is the non-observed location to be estimated. It is assumed that one connected vehicle 42 (connected vehicle 42A) and several unconnected vehicles 44 are traveling at non-observed location A.

[0051] In the example shown in Figure 6(A), the CPU 21 identifies the connected vehicle 42A traveling at non-observation point A based on observation information and vehicle information transmitted from the connected vehicle 42 traveling on the road. In this case, the CPU 21 acquires the traffic volume of the connected vehicle 42 at non-observation point A as "1 vehicle". Next, the CPU 21 identifies the observation point A that the connected vehicle 42A most recently passed through, based on the trajectory formed by the location information contained in the vehicle information transmitted from the connected vehicle 42A and the observation information. Then, the CPU 21 acquires the traffic volume ratio of observation point A closest to the current date and time from the traffic volume ratios of observation points stored in the memory unit 24. For example, if the current date and time is "8:30", the CPU 21 acquires the traffic volume ratio of observation point A corresponding to the time period from 8:00 to 9:00. Here, the acquired traffic volume ratio of observation point A is "3:1".

[0052] The CPU 21 then estimates the total traffic volume at non-observation point A based on the traffic volume of connected vehicle 42 at non-observation point A, which is "1 vehicle," and the traffic volume ratio at observation point A corresponding to the 8:00 to 9:00 time period, which is "3:1." In this case, the CPU 21 estimates the total traffic volume at non-observation point A as "3 vehicles" based on "1 × 3 = 3."

[0053] Figure 6(B) is a second explanatory diagram illustrating a specific example of the total traffic volume at a non-observed location estimated by the CPU 21. Similar to Figure 6(A), Figure 6(B) shows vehicles 40 traveling at non-observed location A, which is the non-observed location to be estimated. It is assumed that two connected vehicles 42 (connected vehicle 42A and connected vehicle 42B) and several unconnected vehicles 44 are traveling at non-observed location A.

[0054] In the example shown in Figure 6(B), the CPU 21 identifies connected vehicles 42A and 42B traveling at non-observation point A based on observation information and vehicle information transmitted from connected vehicles 42 traveling on the road. In this case, the CPU 21 obtains the traffic volume of connected vehicles 42 at non-observation point A as "2 vehicles". Next, the CPU 21 identifies observation points A and B that connected vehicles 42A and 42B most recently passed, based on the trajectories formed by the location information contained in the vehicle information transmitted from connected vehicles 42A and 42B, respectively, and the observation information. Then, the CPU 21 obtains the traffic volume ratios for observation points A and B that are closest to the current date and time from the traffic volume ratios of observation points stored in the memory unit 24. For example, if the current date and time is "8:30", the CPU 21 obtains the traffic volume ratios for observation points A and B that correspond to the time period from 8:00 to 9:00. Here, the traffic volume ratio at observation point A is assumed to be "3:1", and the traffic volume ratio at observation point B is assumed to be "2:1".

[0055] The CPU 21 then estimates the total traffic volume at non-observation point A based on the traffic volume of connected vehicles 42 at non-observation point A, which is "2 vehicles", the traffic volume ratio at observation point A, which is "3:1", and the traffic volume ratio at observation point B, which is "2:1". In this way, if there are multiple connected vehicles 42 traveling at the non-observation point to be estimated, the CPU 21 averages the traffic volume ratios of the observation points that each connected vehicle 42 has most recently passed. The CPU 21 then estimates the total traffic volume at the non-observation point to be estimated based on the average traffic volume ratio and the traffic volume of connected vehicles 42 at the non-observation point to be estimated. In the above case, the CPU 21 calculates the average traffic volume ratio as {(3×1)+(2×1)}÷2=2.5, and sets it to "2.5:1". The CPU 21 then estimates the total traffic volume at non-observation point A as "5 vehicles" with "2×2.5=5".

[0056] As explained above, in server 20, the CPU 21 acquires the total traffic volume at the observation point and the location information of connected vehicles 42 on the entire road. Then, the CPU 21 estimates the total traffic volume at the target non-observation point based on the traffic volume ratio of the observation point that the connected vehicle 42 traveling at the target non-observation point passed most recently, and the traffic volume of the connected vehicle 42 at the target non-observation point. As a result, server 20 can estimate the total traffic volume at the non-observation point based on the location information of the connected vehicle 42 transmitted from the connected vehicle 42 and the total traffic volume at the observation point. Furthermore, since server 20 can estimate the total traffic volume at the non-observation point based on the total traffic volume at the observation point, the measurement cost of manually measuring the traffic volume at the non-observation point by surveyors is reduced. Note that the above estimation of the total traffic volume at the non-observation point is based on the assumption that the connected vehicle 42 and the non-connected vehicle 44 have the same movement tendency.

[0057] Furthermore, in server 20, if there are multiple connected vehicles 42 traveling at the non-observed location to be estimated, the CPU 21 estimates the total traffic volume at the non-observed location to be estimated based on the traffic volume ratio of the observation locations that each of the multiple connected vehicles 42 has most recently passed, and the traffic volume of the connected vehicles 42 at the non-observed location to be estimated. As a result, server 20 can estimate the total traffic volume at the non-observed location based on the total traffic volume of the observation locations that each of the multiple connected vehicles 42 has most recently passed.

[0058] Furthermore, in server 20, the CPU 21 estimates the total traffic volume of a predetermined observation point (hereinafter referred to as "the observation point to be estimated"), which is specified by the user, based on the traffic volume ratio of that observation point and the traffic volume of connected vehicles 42 at the observation point to be estimated. In this way, server 20 can also estimate the total traffic volume of the observation point.

[0059] Furthermore, in server 20, the period during which CPU 21 estimates the total traffic volume at the observation point is shorter than the period during which CPU 21 acquires the total traffic volume at the observation point. As a result, server 20 can grasp the total traffic volume at the observation point by estimating it, without waiting for the acquisition of that total traffic volume. In other words, server 20 can estimate the total traffic volume at the observation point in near real time without waiting for the transmission of observation information from observation device 60.

[0060] Furthermore, in server 20, the CPU 21 estimates the total traffic volume for the non-observed locations or observed locations to be estimated, based on the traffic volume ratio closest to the current date and time. This allows server 20 to estimate the total traffic volume based on a highly reliable traffic volume ratio corresponding to the time period closest to the current date and time.

[0061] (others) In the above embodiment, the observation device 60 was described as a computer device installed at an observation point, but the observation device 60 is not limited to being installed at an observation point. For example, the observation device 60 may be a computer device owned by a surveyor conducting a traffic volume survey. In this case, the traffic volume at the observation point, measured manually by the surveyor, is input to the observation device 60, and the input traffic volume is transmitted to the server 20 as observation information.

[0062] In the above embodiment, the unit periods for each process were exemplified as the past month and the past day, but the unit periods are not limited to these. For example, the CPU 21 may input the image information of each group within the past two months as the first unit period, and one week's worth of image information as the second unit period, which is shorter than the first unit period, into the trained model.

[0063] In the above embodiment, the CPU 21 calculated the traffic volume ratio at the observation point by dividing it into hourly time periods, but the interval at which the traffic volume ratio at the observation point is divided is not limited to one hour. For example, the CPU 21 may calculate the traffic volume ratio at the observation point by dividing it into time periods of two hours or three hours, etc., as predetermined time periods.

[0064] In the above embodiment, the CPU 21 used the traffic volume ratio closest to the current date and time to estimate the total traffic volume. However, it is not limited to this, and other factors besides time may be included in the criteria for selecting the traffic volume ratio. For example, the CPU 21 may further classify the traffic volume ratios of observation points calculated for each predetermined time period into weekdays and weekends / holidays and store them in the storage unit 24. In this case, the CPU 21 selects the traffic volume ratio that corresponds to the type of estimation day (whether it is a weekday or a weekend / holiday) and is closest to the current date and time, and uses it to estimate the total traffic volume.

[0065] In the above embodiment, the CPU 21 identified the traffic volume of the connected vehicle 42 on the entire road based on vehicle information transmitted from the connected vehicle 42. In addition, other information may be identified based on the vehicle information. For example, the CPU 21 may identify the branching rates of the connected vehicle 42 at each intersection, such as going straight, turning right, turning left, and making a U-turn, from the trajectory formed by the position information contained in the vehicle information transmitted from the connected vehicle 42. Furthermore, the CPU 21 may identify the travel speed of the connected vehicle 42 at each observation point and each non-observation point from the trajectory and the time information contained in the vehicle information. As a result, the estimation system 10 can estimate not only the total traffic volume on the entire road, but also the branching rates at each intersection on the entire road and the travel speed on the entire road, enabling a more detailed simulation of the road.

[0066] In the above embodiment, an embodiment was described in which the information processing program 24A is pre-stored (installed) in the storage unit 24, but the embodiment is not limited to this. The information processing program 24A may be provided in the form of being recorded on a recording medium such as a CD-ROM (Compact Disk Read Only Memory), DVD-ROM (Digital Versatile Disk Read Only Memory), and USB (Universal Serial Bus) memory. Alternatively, the information processing program 24A may be provided in the form of being downloaded from an external device via a network. [Explanation of Symbols]

[0067] 20 Servers (Information Processing Devices) 21A Acquisition Department 21C Estimation part 40 vehicles 42 Connected Vehicle (Vehicle 1) 44 Non-connected vehicle (Vehicle 2)

Claims

1. An acquisition unit that acquires the total traffic volume, which is the total traffic volume of all vehicles including a first vehicle that can transmit its own location information and a second vehicle that cannot transmit the location information, output from a trained model that has been trained to output a value that measures the traffic volume of vehicles traveling at the observation point from an image of the observation point where the total traffic volume is observed, and the location information of the first vehicle for the entire road including the observation point and non-observation points where the total traffic volume is not observed. Based on the trajectory formed by the position information of the first vehicle acquired by the acquisition unit, the branching ratio of straight, right turn, left turn, and U-turn at each intersection of the first vehicle is determined, and based on the trajectory and the time information included in the position information, the travel speed of the first vehicle at the observation point and the non-observation point is determined by the identification unit. An estimation unit estimates the total traffic volume at the non-observation point based on the traffic volume ratio, which is the ratio of the total traffic volume at the observation point most recently passed by the first vehicle traveling at the non-observation point to the traffic volume of the first vehicle, and the traffic volume of the first vehicle at the non-observation point, calculated from the total traffic volume at the observation point and the position information of the first vehicle on the entire road acquired by the acquisition unit, and the traffic volume of the first vehicle at the non-observation point. Equipped with, Information processing device.

2. The estimation unit estimates the total traffic volume at the non-observation point based on the average of the traffic volume ratios of the observation points that each of the multiple first vehicles has most recently passed, and the traffic volume of the first vehicles at the non-observation point, when there are multiple first vehicles traveling at the non-observation point. The information processing apparatus according to claim 1.

3. The estimation unit estimates the total traffic volume at a predetermined observation point based on the traffic volume ratio at a predetermined observation point and the traffic volume of the first vehicle at the predetermined observation point, which are calculated from the total traffic volume at the observation point and the position information of the first vehicle on the entire road, obtained by the acquisition unit. The information processing apparatus according to claim 1.

4. The period during which the estimation unit estimates the total traffic volume at a predetermined observation point is shorter than the period during which the acquisition unit acquires the total traffic volume at the observation point. The information processing apparatus according to claim 3.

5. If multiple traffic volume ratios are provided for each observation point according to the time of day, the estimation unit estimates the total traffic volume for the non-observation point or a predetermined observation point based on the traffic volume ratio closest to the current date and time. The information processing apparatus according to claim 1 or 3.

Images